© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12253
    Prev
    Next
    INDEX
    Explanations

    key concepts related to the act of discussing or analyzing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions of direction

    np_acts-logits-general · gemini-2.0-flash

    directional particles following verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOSIS
    -0.60
    BIDDEN
    -0.55
    laise
    -0.53
    ]--;
    -0.52
     riuscito
    -0.52
    tomans
    -0.52
    withIdentifier
    -0.50
    越好
    -0.49
    spent
    -0.48
    UNS
    -0.47
    POSITIVE LOGITS
     down
    1.21
     off
    1.09
     up
    1.00
     away
    0.97
     out
    0.96
     apart
    0.90
     aside
    0.85
     asunder
    0.81
     back
    0.80
     forward
    0.79
    Activations Density 0.375%

    No Known Activations